Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 364 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7946. Min Act: -0.0001

Data Index: 1527230 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.8297. Min Act: -0.0001

Data Index: 1381637 (Python Code)

Max Activating Token Index: 752

Text #2

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7829. Min Act: -0.0001

Data Index: 1655353 (Python Code)

Max Activating Token Index: 725

Text #3

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7769. Min Act: -0.0001

Data Index: 1582034 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7269. Min Act: -0.0001

Data Index: 1651042 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6726. Min Act: -0.0001

Data Index: 1382898 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7655. Min Act: -0.0001

Data Index: 1365782 (Python Code)

Max Activating Token Index: 618

Text #7

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7349. Min Act: -0.0001

Data Index: 1554984 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7545. Min Act: -0.0001

Data Index: 1385714 (Python Code)

Max Activating Token Index: 998

Text #9

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1517589 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7418. Min Act: -0.0001

Data Index: 1642182 (Python Code)

Max Activating Token Index: 754

Text #11

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7350. Min Act: -0.0001

Data Index: 1442412 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6893. Min Act: -0.0001

Data Index: 1590424 (Python Code)

Max Activating Token Index: 665

Text #13

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1636645 (Python Code)

Max Activating Token Index: 673

Text #14

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6871. Min Act: -0.0001

Data Index: 1585484 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7323. Min Act: -0.0001

Data Index: 1468796 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6824. Min Act: -0.0001

Data Index: 1601980 (Python Code)

Max Activating Token Index: 805

Text #17

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1420266 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6607. Min Act: -0.0001

Data Index: 1444660 (Python Code)

Max Activating Token Index: 659

Text #19

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6627. Min Act: -0.0001

Data Index: 1378457 (Python Code)

Max Activating Token Index: 61